This Code is used to analyze the Positive and Negative given by the customers for a Women's E-commerce Clothing Website.

This Code is installing the Gensim.Gensim is an open source library unsupervised topic modeling and natural language processing.

This is used to import all the necessary packages.NLTK modules define various interfaces which can be used to download corpora, model and other data packages that can be used with the kit. "punkt" is a required package for tokenization.

This code snippet helps us to read the data, and open the dataset.

This code is to print single lines from the dataset.

This method is used to compile a regular expression pattern provided as a string into a regex pattern object.

Pre- processing : The below code snippet helps to print the lines and tokenize the dataset. Tokenization is the process of breaking the string into pieces such as words, sentences. The tokens as part of the preprocessing step is converted into lower case.

Pre-Processing step of removing punctuations and any other characters leaving alpha numeric values.

The below code snippet helps to print the lines and tokenize the dataset. Tokenization is the process of breaking the string into pieces such as words, sentences.

This code helps to implement the word2vec family of algorithms, using highly optimized C routines, data streaming and Pythonic interfaces. We save the data model for later training. The bin file is created. Load() is used to load a previosuly saved Word2Vec model.Here the W2V model is using skip gram model where the model learns the neighbouring words based on the given "focus word". Converting into bin file : -m gensim.scripts.word2vec2tensor -i C:\Users\HP\OneDrive\Documents\AI\sample_model1.bin -o C:\Users\HP\OneDrive\Documents\AI\

Here the W2V model is using skip gram model where the model learns the neighbouring words based on the given "focus word".

Here the W2V model is using skip gram model where the model learns the neighbouring words based on the given "focus word".

This code is used to access the vector representation of any word in the vocabulary.

The below code saves all the adjectives that incline towards the customers who have provided negative review.

The below code saves all the adjectives that incline towards the customers who have provided positive review

The below code saves the final model into a .bin file format. This data is used in Tensorflow to visualise the data.